Spaces:
Duplicated from uonlp/open_multilingual_llm_leaderboard

BramVanroy
/

open_dutch_llm_leaderboard

Running

App Files Files Community

open_dutch_llm_leaderboard / evals

Commit History

add evals

5603395

Bram Vanroy commited on Jan 20

add evals

bf2aa55

Bram Vanroy commited on Jan 12

add tower details

c4fecca

Bram Vanroy commited on Jan 12

add first Tower

e6a7a63

Bram Vanroy commited on Jan 12

add Yi mmlu

4228cee

Bram Vanroy commited on Dec 30, 2023

complete Phi 2

2e653e4

Bram Vanroy commited on Dec 30, 2023

add evals

d20fb33

Bram Vanroy commited on Dec 29, 2023

add first Yi chat

3b045b8

Bram Vanroy commited on Dec 27, 2023

add GEITJE mmlu

7f88a71

Bram Vanroy commited on Dec 18, 2023

update models

9739433

Bram Vanroy commited on Dec 18, 2023

Merge branch 'main' of https://huggingface.co/spaces/BramVanroy/open_dutch_llm_leaderboard

cb090d6

Bram Vanroy commited on Dec 18, 2023

add Mistral evals

38b8e33

Bram Vanroy commited on Dec 18, 2023

orca was instruction tuned

8a10664

Bram Vanroy commited on Dec 17, 2023

fix RL llama 2 chat

3984712

Bram Vanroy commited on Dec 17, 2023

remove mixtral for now

aeb0be7

Bram Vanroy commited on Dec 17, 2023

fix merge

dbe0b3a

Bram Vanroy commited on Dec 17, 2023

add geitje

6a37317

Bram Vanroy commited on Dec 17, 2023

remove mixtral - was not tested in 8-bit

0658988

Bram Vanroy commited on Dec 13, 2023

add correct evals:

351f9fe

Bram Vanroy commited on Dec 13, 2023

fix retention of fields

b1e6575

Bram Vanroy commited on Dec 13, 2023

update models.json

08f6f54

Bram Vanroy commited on Dec 13, 2023

add mixtral hellaswag

0c3ae1e

Bram Vanroy commited on Dec 13, 2023

update display

8e901a2

Bram Vanroy commited on Dec 7, 2023

generate models.json

fc44f1d

Bram Vanroy commited on Dec 6, 2023

always lower case shortname

107c2a4

Bram Vanroy commited on Dec 6, 2023

add models.json

2686c5b

Bram Vanroy commited on Dec 6, 2023

add data collection script

828458d

Bram Vanroy commited on Dec 6, 2023

rm llama/bloom evaluations

d081f4d

Bram Vanroy commited on Dec 6, 2023

add evaluations

d64c180

Bram Vanroy commited on Dec 6, 2023

add evaluations

4a78e88

Bram Vanroy commited on Dec 3, 2023

add evaluations

41e053a

Bram Vanroy commited on Dec 2, 2023

add evaluations

adbc35a

Bram Vanroy commited on Dec 2, 2023

add evaluations

6b009a1

Bram Vanroy commited on Dec 2, 2023

add evaluations

4e9723c

Bram Vanroy commited on Dec 1, 2023

add evaluations

9c8bb6d

Bram Vanroy commited on Dec 1, 2023

add evaluations

0b1977f

Bram Vanroy commited on Dec 1, 2023

add evals

851256b

Bram Vanroy commited on Nov 30, 2023

add evaluations

90df5ea

Bram Vanroy commited on Nov 30, 2023

add evaluations

11b505c

Bram Vanroy commited on Nov 30, 2023

add mmlu evals

d1293bd

Bram Vanroy commited on Nov 28, 2023

add evaluations

1303fdd

Bram Vanroy commited on Nov 28, 2023

add evaluations

58724a6

Bram Vanroy commited on Nov 27, 2023

add data

3b151fc

Bram Vanroy commited on Nov 27, 2023

remove hellaswag

6087d40

Bram Vanroy commited on Nov 26, 2023

revision for Dutch only

5693ee5

Bram Vanroy commited on Nov 26, 2023

update with only Dutch

863e074

Bram Vanroy commited on Nov 24, 2023

Rename evals/truthfulqa/truthfulqa_nl_llama2-13b-ft-mc4_nl_cleaned_tiny.json to evals/truthfulqa/truthfulqa_nl-llama2-13b-ft-mc4_nl_cleaned_tiny.json

ae38e13

BramVanroy commited on Nov 10, 2023

Rename evals/truthfulqa/truthfulqa_nl_falcon-40b.json to evals/truthfulqa/truthfulqa_nl-falcon-40b.json

54814fe

BramVanroy commited on Nov 10, 2023

Rename evals/truthfulqa/truthfulqa_nl_falcon-40b-ft-alpaca-dolly-dutch.json to evals/truthfulqa/truthfulqa_nl-falcon-40b-ft-alpaca-dolly-dutch.json

1f6eae8

BramVanroy commited on Nov 10, 2023

Rename evals/truthfulqa/truthfulqa_nl_Llama-2-13b-hf.json to evals/truthfulqa/truthfulqa_nl-Llama-2-13b-hf.json

677112c

BramVanroy commited on Nov 10, 2023